155 research outputs found
Results of the european land robot trial and their usability for benchmarking outdoor robot systems
No full textS.408-409It is generally a problematic task to compare different approaches and methods in the field of outdoor robotics [1]. In the majority of cases, results are reported only for a specific robotic system. All tasks are solved in a static and often specially defined environment, making it hard to compare the outcome with results from other research groups, other approaches, and other robots. The commonly used means of "proof by video" or "proof by (one) example" are insufficient for obvious reasons. As one possible solution, robot competitions can be a benchmark for real robot systems [2]
Data Synthesization for Classification in Autonomous Robotic Grasping System Using ‘Catalogue’-Style Images
No full textThe classification and grasping of randomly placed objects where only a limited number of training images are available, remains a challenging problem. Approaches such as data synthesis have been used to synthetically create larger training data sets from a small set of training data and can be used to improve performance. This paper examines how limited product images for ‘off the shelf’ items can be used to generate a synthetic data set that is used to train a that allows classification of the item, segmentation and grasping. Experiments investigating the effects of data synthesis are presented and the subsequent trained network implemented in a robotic system to perform grasping of objects. © Springer International Publishing AG, part of Springer Nature 2018.CREATE-LA
Towards Autonomous Robotic Systems: 24th Annual Conference, TAROS 2023, Cambridge, UK, September 13–15, 2023, Proceedings
No full textConference proceedings info: TAROS 2023.This book constitutes the refereed proceedings of the 24th Annual Conference Towards Autonomous Robotic Systems, TAROS 2023, held in Cambridge, UK, during September 13–15, 2023. The 40 full papers presented in this book were carefully reviewed and selected from 70 submissions.
They cover a wide range of different topics such as: agri-food robotics; autonomy; collaborative and service robotics; locomotion and manipulation; machine vision; multi-robot systems; soft robotics; tactile sensing; and teleoperation
Soft Fiber-Reinforced Pneumatic Actuator Design and Fabrication: Towards Robust, Soft Robotic Systems
No full text© Springer Nature Switzerland AG 2019. Soft robotics is a rapidly evolving, young research area. So far there are no well-established design standards nor fabrication procedures for soft robots. A number of research groups are working on soft robotics solutions independently and we can observe a range of designs realized in different ways. These soft robots are based on various actuation principles, are driven with various actuation media, and offer various actuation properties. Still, most of them require lots of manual effort and high manual fabrication skills from the person manufacturing these kinds of robots. A significant share of the proposed designs suffers from some imperfections that could be improved by simple design changes. In this work, we propose a number of design and fabrication rules for improving the performance and fabrication complexity of soft fiber-reinforced pneumatic actuators. The proposed design approach focuses on a circular geometry for the pressure chambers and applying a dense, fiber-based reinforcement. Such an approach allows for a more linear actuator response and reduced wear of the actuators, when compared to previous approaches. The proposed manufacturing procedure introduces the application of the reinforcement before the fabrication of the actuator body, significantly reducing the required fabrication effort and providing more consistent and more reliable results
A validation of localisation accuracy improvements by the combined use of GPS and GLONASS
No full textS.374-375For autonomous navigation in outdoor environments, robust and reliable positioning is an indispensable prerequisite. Looking at unstructured or a priori unknown surroundings the use of global navigation satellite systems (GNSS) is a reasonable approach [1]. The Global Positioning System (GPS) is definitely the most popular GNSS. There are several efforts to build competing GNSS, from which only the Russian GLONASS is nearly operational. Nowadays, even recreation-grade GPS receivers often achieve an accuracy of less than 10m. But, since this is still not enough for many localisation and navigation tasks, several techniques have been developed to improve the positioning accuracy. In principle, all these methods use differential data coming from a base station at a well-known position. The GPS receiver applies the differential information in order to eliminate error sources like signal delays or inaccurate satellite orbits. Depending on the used method, this is called Code Differential GPS (DGPS) or Real Time Kinematics (RTK). Using sufficiently sophisticated receivers, with DGPS accuracy in the metre range can be reached. For RTK systems centimetre or even millimetre ranges are achievable
Real-world, real-time robotic grasping with convolutional neural networks
No full textAdapting to uncertain environments is a key obstacle in the development of robust robotic object manipulation systems, as there is a trade-off between the computationally expensive methods of handling the surrounding complexity, and the real-time requirement for practical operation. We investigate the use of Deep Learning to develop a real-time scheme on a physical robot. Using a Baxter Research Robot and Kinect sensor, a convolutional neural network (CNN) was trained in a supervised manner to regress grasping coordinates from RGB-D data. Compared to existing methods, regression via deep learning offered an efficient process that learnt generalised grasping features and processed the scene in real-time. The system achieved a successful grasp rate of 62% and a successful detection rate of 78% on a diverse set of physical objects across varying position and orientation, executing grasp detection in 1.8 s on a CPU machine and a complete physical grasp and move in 60 s on the robot. © Springer International Publishing AG 2017.CREATE-LA
Towards Automated Surgical Robotics: a Requirements Engineering Approach
No full textThe paper describes a design specification process
for the development of novel and intelligent surgical robots.
Nowadays, surgical robots are usually controlled by the surgeons
manually by using teleoperation. The possibility to carry
out simple surgical actions automatically has been the subject
of academical research, but very few real-world applications
exist. The main objective of this research is to address realistic
case studies and develop systems and methods to provide
surgeons with autonomous robotic assistants, performing basic
surgical actions by combining sensing, dexterity and cognitive
capabilities. This goal can only be achieved by means of
a formal and rigorous assesment of surgical requirements,
so that they can be analysed and translated into behavioral
specifications for an autonomous robotic system. Therefore, the
paper describes the application of Requirements Engineering to
surgical knowledge formalization and propose a methodology
for the transformation of requirements into formal models of
robotic tasks
The design and intelligent control of an autonomous mobile robot
No full textThis thesis presents an investigation into the problems of exploration, map building and collision free navigation for intelligent autonomous mobile robots. The project began with an extensive review of currently available literature in the field of mobile robot research, which included intelligent control techniques and their application. It became clear that there was scope for further development with regard to map building and exploration in new and unstructured environments. Animals have an innate propensity to exhibit such abilities, and so the analogous use of artificial neural networks instead of actual neural systems was examined for use as a method of robot mapping. A simulated behaviour based mobile robot was used in conjunction with a growing cell structure neural network to map out new environments. When using the direct application of this algorithm, topological irregularities were observed to be the direct result of correlations within the input data stream. A modification to this basic system was shown to correct the problem, but further developments would be required to produce a generic solution. The mapping algorithms gained through this approach, although more similar to biological systems, are computationally inefficient in comparison to the methods which were subsequently developed. A novel mapping method was proposed based on the robot creating new location vectors, or nodes, when it exceeded a distance threshold from its mapped area. Network parameters were developed to monitor the state of growth of the network and aid the robot search process. In simulation, the combination of the novel mapping and search process were shown to be able to construct maps which could be subsequently used for collision free navigation. To develop greater insights into the control problem and to validate the simulation work the control structures were ported to a prototype mobile robot. The mobile robot was of circular construction, with a synchro-drive wheel configuration, and was equipped with eight ultrasonic distance sensors and an odometric positioning system. It was self-sufficient, incorporating all its power and computational resources. The experiments observed the effects of odometric drift and demonstrated methods of re-correction which were shown to be effective. Both the novel mapping method, and a new algorithm based on an exhaustive mesh search, were shown to be able to explore different environments and subsequently achieve collision free navigation. This was shown in all cases by monitoring the estimates in the positional error which remained within fixed bounds
3D printed sensorized soft robotic manipulator design
No full textAnthropomorphic soft robotics systems which replicate the stiffness and range of human joints can be challenging to develop and fabricate. By using 3D printing it is possible to create flexible joints which can have the mechanical impedance and joint range determined by the physical parameters; this allows compliant manipulators to be produced from rigid materials in a single 3D print. The dexterity of the fingers developed using rapid prototyping methods has been demonstrated by using the approach with soft manipulators to handle chopsticks to grip objects. © Springer International Publishing AG 2017.CREATE-LABThanks to Frank Clemens (EMPA) for providing assistance and CTPE. This project was funded by the EPSRC CDT in Sensor Technologies (Grant EP/L015889/1)
Evaluating the effect of robot group size on relative localisation precision
No full textS.149-160Looking on co-operative position estimation in multi-robot systems, the question to what extend the number of robots has an influence on the quality of the resulting localisation is an important and interesting issue. This paper addresses this relation regarding a pure relative localisation approach based only on mutual observations between the robots. The intuitive expectation that more robots should improve the position estimation is motivated and the design of the experiments with special respect to possibly distorting parameters is discussed and reasoned in detail. An in-depth analysis of the collected data explains the only partial conformance of the experimental results with the expected outcome
- …
